Wednesday, September 11, 2024

Mistral releases its first multimodal model, Pixtral 12B, available on GitHub and Hugging Face, and via API "soon" (Kyle Wiggers/TechCrunch)

Kyle Wiggers / TechCrunch:
Mistral releases its first multimodal model, Pixtral 12B, available on GitHub and Hugging Face, and via API “soon”  —  French AI startup Mistral has released its first model that can process images as well as text.  —  Called Pixtral 12B, the 12-billion-parameter model is roughly 24GB in size.



at
Labels:

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

A look at the troubled rollout of the EU's automated biometric entry/exit border system, as airport operators warn of severe delays ahead of the summer holidays (Financial Times)

Financial Times : A look at the troubled rollout of the EU's automated biometric entry/exit border system, as airport operators warn o...